Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    apologize, apollo, apocrypha, aperitivo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PDEs
    0.47
     சொல்க
    0.46
     baggy
    0.45
    妫
    0.45
     PAINE
    0.45
    ᕕ
    0.44
     поги
    0.44
     الشيطان
    0.43
     HUOBI
    0.43
     unbear
    0.42
    POSITIVE LOGITS
    Ap
    0.97
     Ap
    0.89
     ap
    0.88
     AP
    0.88
    AP
    0.78
     एपी
    0.70
     ап
    0.70
     آپ
    0.64
     Ape
    0.61
     апо
    0.61
    Act Density 0.055%

    No Known Activations